c45loader.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

/*
 *    This program is free software; you can redistribute it and/or modify
 *    it under the terms of the GNU General Public License as published by
 *    the Free Software Foundation; either version 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU General Public License for more details.
 *
 *    You should have received a copy of the GNU General Public License
 *    along with this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 *    C45Loader.java
 *    Copyright (C) 2000 Mark Hall
 *
 */

package weka.core.converters;

import weka.core.Attribute;
import weka.core.FastVector;
import weka.core.Instance;
import weka.core.Instances;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.io.StreamTokenizer;

/**
 <!-- globalinfo-start -->
 * Reads a file that is C45 format. Can take a filestem or filestem with .names or .data appended. Assumes that path/&lt;filestem&gt;.names and path/&lt;filestem&gt;.data exist and contain the names and data respectively.
 * <p/>
 <!-- globalinfo-end -->
 * 
 * @author Mark Hall ([e-mail])
 * @version $Revision: 1.11 $
 * @see Loader
 */
public class C45Loader 
  extends AbstractLoader 
  implements FileSourcedConverter, BatchConverter, IncrementalConverter {

  /** for serialization */
  static final long serialVersionUID = 5454329403218219L;
  
  /** the file extension */
  public static String FILE_EXTENSION = ".names";

  /** the file */
  protected String m_File = 
    (new File(System.getProperty("user.dir"))).getAbsolutePath();
  
  /**
   * Holds the determined structure (header) of the data set.
   */
  //@ protected depends: model_structureDetermined -> m_structure;
  //@ protected represents: model_structureDetermined <- (m_structure != null);
  protected Instances m_structure = null;

  /**
   * Holds the source of the data set. In this case the names file of the
   * data set. m_sourceFileData is the data file.
   */
  //@ protected depends: model_sourceSupplied -> m_sourceFile;
  //@ protected represents: model_sourceSupplied <- (m_sourceFile != null);
  protected File m_sourceFile = null;

  /**
   * Describe variable <code>m_sourceFileData</code> here.
   */
  private File m_sourceFileData = null;

  /**
   * Reader for names file
   */
  private transient Reader m_namesReader = null;

  /**
   * Reader for data file
   */
  private transient Reader m_dataReader = null;

  /**
   * Holds the filestem.
   */
  private String m_fileStem;

  /**
   * Number of attributes in the data (including ignore and label attributes).
   */
  private int m_numAttribs;

  /**
   * Which attributes are ignore or label. These are *not* included in the
   * arff representation.
   */
  private boolean [] m_ignore;

  /**
   * Returns a string describing this attribute evaluator
   * @return a description of the evaluator suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return "Reads a file that is C45 format. Can take a filestem or filestem "
      +"with .names or .data appended. Assumes that path/<filestem>.names and "
      +"path/<filestem>.data exist and contain the names and data "
      +"respectively.";
  }
  
  /**
   * Resets the Loader ready to read a new data set
   * 
   * @throws Exception if something goes wrong
   */
  public void reset() throws Exception {
    m_structure = null;
    setRetrieval(NONE);
    if (m_File != null) {
      setFile(new File(m_File));
    }
  }

  /**
   * Get the file extension used for arff files
   *
   * @return the file extension
   */
  public String getFileExtension() {
    return FILE_EXTENSION;
  }

  /**
   * Returns a description of the file type.
   *
   * @return a short file description
   */
  public String getFileDescription() {
    return "C4.5 data files";
  }

  /**
   * get the File specified as the source
   *
   * @return the source file
   */
  public File retrieveFile() {
    return new File(m_File);
  }

  /**
   * sets the source File
   *
   * @param file the source file
   * @exception IOException if an error occurs
   */
  public void setFile(File file) throws IOException {
    m_File = file.getAbsolutePath();
    setSource(file);
  }

  /**
   * Resets the Loader object and sets the source of the data set to be 
   * the supplied File object.
   *
   * @param file the source file.
   * @exception IOException if an error occurs
   */
  public void setSource(File file) throws IOException {
    
    m_structure = null;
    setRetrieval(NONE);

    if (file == null) {
      throw new IOException("Source file object is null!");
    }

    String fname = file.getName();
    String fileStem;
    String path = file.getParent();
    if (path != null) {
      path += File.separator;
    } else {
      path = "";
    }
    if (fname.indexOf('.') < 0) {
      fileStem = fname;
      fname += ".names";
    } else {
      fileStem = fname.substring(0, fname.lastIndexOf('.'));
      fname = fileStem + ".names";
    }
    m_fileStem = fileStem;
    file = new File(path+fname);

    m_sourceFile = file;
    try {
      BufferedReader br = new BufferedReader(new FileReader(file));
      m_namesReader = br;
    } catch (FileNotFoundException ex) {
      throw new IOException("File not found : "+(path+fname));
    }

    m_sourceFileData = new File(path+fileStem+".data");
    try {
      BufferedReader br = new BufferedReader(new FileReader(m_sourceFileData));
      m_dataReader = br;
    } catch (FileNotFoundException ex) {
      throw new IOException("File not found : "+(path+fname));
    }
    m_File = file.getAbsolutePath();
  }

  /**
   * Determines and returns (if possible) the structure (internally the 
   * header) of the data set as an empty set of instances.
   *
   * @return the structure of the data set as an empty set of Instances
   * @exception IOException if an error occurs
   */
  public Instances getStructure() throws IOException {
    if (m_sourceFile == null) {
      throw new IOException("No source has beenspecified");
    }

    if (m_structure == null) {
      setSource(m_sourceFile);
      StreamTokenizer st = new StreamTokenizer(m_namesReader);
      initTokenizer(st);
      readHeader(st);
    }
    
    return m_structure;
  }

  /**
   * Return the full data set. If the structure hasn't yet been determined
   * by a call to getStructure then method should do so before processing
   * the rest of the data set.
   *
   * @return the structure of the data set as an empty set of Instances
   * @exception IOException if there is no source or parsing fails
   */
  public Instances getDataSet() throws IOException {
    if (m_sourceFile == null) {
      throw new IOException("No source has been specified");
    }
    if (getRetrieval() == INCREMENTAL) {
      throw new IOException("Cannot mix getting Instances in both incremental and batch modes");
    }
    setRetrieval(BATCH);
    if (m_structure == null) {
      getStructure();
    }
    StreamTokenizer st = new StreamTokenizer(m_dataReader);
    initTokenizer(st);
    //    st.ordinaryChar('.');
    Instances result = new Instances(m_structure);
    Instance current = getInstance(st);

    while (current != null) {
      result.add(current);
      current = getInstance(st);
    }
    try {
      reset();